INS-ActBench: A Comprehensive Benchmark for Assessing Professional Actuarial Capability of Large Language Models
2026-07-27 • Computation and Language
Computation and Language
AI summaryⓘ
The authors created INS-ActBench, a new test set to check how well large language models (LLMs) can do actuarial tasks that professionals face. This test includes questions about basic actuarial knowledge, analyzing long insurance cases, and doing spreadsheet and coding tasks with exact numbers. They tested several LLMs and human experts, finding that LLMs are good at standard knowledge but not as strong at complex case reasoning or practical tool use. INS-ActBench aims to help improve LLMs for real-world actuarial work. The authors also shared their code for others to use.
Large Language ModelsActuarial ScienceBenchmarkNumerical ReasoningLong-context UnderstandingTool UseSpreadsheet TasksR-codeJurisdiction-sensitive PracticeProfessional Workflows
Authors
Changyu Chen, Chenwei Lin, Xian Xu
Abstract
Large Language Models (LLMs) have shown strong potential in financial reasoning, but existing benchmarks often evaluate domain knowledge, numerical reasoning, long-context understanding, and tool use in separate settings. This limits their ability to assess realistic professional workflows that require auditable, context-grounded, and tool-executable decisions. We introduce \textbf{INS-ActBench}, a comprehensive benchmark for evaluating professional actuarial capability in LLMs. INS-ActBench contains 12,050 Q\&A pairs from public exams and sample questions released by 16 actuarial associations. It covers three subsets: \textbf{INS-Act-Know} for standardized actuarial knowledge, \textbf{INS-Act-Case} for long-context insurance case reasoning, and \textbf{INS-Act-Practice} for spreadsheet and R-code tasks with verifiable numerical outputs. Experiments on nine representative LLMs and human actuarial experts reveal a clear capability boundary: frontier LLMs perform strongly on standardized knowledge, but remain much weaker in case reasoning, tool-based workflows, and jurisdiction-sensitive practice. INS-ActBench provides a reproducible foundation for developing actuarial LLMs toward reliable professional assistance. The code is available at https://github.com/FDU-INS/INS-ActBench.